{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T08:04:21Z","timestamp":1784534661799,"version":"3.55.0"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Digital Signal Processing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.dsp.2026.106349","type":"journal-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T06:48:13Z","timestamp":1781592493000},"page":"106349","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["WaCoDepth: Waveform conditioned dual-stage feature fusion network for echo-visual depth estimation"],"prefix":"10.1016","volume":"182","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8527-9826","authenticated-orcid":false,"given":"Wenjie","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baolong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingliang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.dsp.2026.106349_bib0001","series-title":"Proceedings of the ACM International Conference on Multimedia","first-page":"3559","article-title":"Robust multimodal depth estimation using transformer based generative adversarial networks","author":"Khan","year":"2022"},{"key":"10.1016\/j.dsp.2026.106349_bib0002","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2229","article-title":"DALDet: depth-aware learning based object detection for autonomous driving","author":"Hu","year":"2024"},{"key":"10.1016\/j.dsp.2026.106349_bib0003","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9275","article-title":"Depth estimation from camera image and mmwave radar point cloud","author":"Singh","year":"2023"},{"issue":"11","key":"10.1016\/j.dsp.2026.106349_bib0004","doi-asserted-by":"crossref","first-page":"7266","DOI":"10.1109\/TVCG.2024.3456162","article-title":"Depth perception in optical see-through augmented reality: investigating the impact of texture density, luminance contrast, and color contrast","volume":"30","author":"Liu","year":"2024","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"10.1016\/j.dsp.2026.106349_bib0005","series-title":"2024 IEEE International Conference on Robotics and Automation","first-page":"3296","article-title":"Think, act, and ask: open-world interactive personalized robot navigation","author":"Dai","year":"2024"},{"key":"10.1016\/j.dsp.2026.106349_bib0006","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","first-page":"2081","article-title":"Multi-modal fusion of event and RGB for monocular depth estimation using a unified transformer-based architecture","author":"Devulapally","year":"2024"},{"issue":"1","key":"10.1016\/j.dsp.2026.106349_bib0007","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-025-24850-7","article-title":"Optimizing YOLOv11 for automated classification of breast cancer in medical images","volume":"15","author":"Abd El-Hafeez","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.dsp.2026.106349_bib0008","doi-asserted-by":"crossref","unstructured":"W.M. Elmessery, D.V. Maklakov, T.M. El-Messery, D.A. Baranenko, J. Guti\u00e9rrez, M.Y. Shams, T.A. El-Hafeez, S. Elsayed, S.K. Alhag, F.S. Moghanm, et al., Semantic segmentation of microbial alterations based on SegFormer, Front. Plant Sci. 15(2024) 1352935.","DOI":"10.3389\/fpls.2024.1352935"},{"key":"10.1016\/j.dsp.2026.106349_bib0009","series-title":"European Conference on Computer Vision","first-page":"658","article-title":"Visualechoes: spatial image representation learning through echolocation","author":"Gao","year":"2020"},{"key":"10.1016\/j.dsp.2026.106349_bib0010","unstructured":"L. Zhu, E. Rahtu, H. Zhao, Beyond visual field of view: perceiving 3D environment with echoes and vision, 2022, arXiv preprint arXiv: 2207.01136."},{"key":"10.1016\/j.dsp.2026.106349_bib0011","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8268","article-title":"Beyond image to depth: improving depth prediction using echoes","author":"Parida","year":"2021"},{"key":"10.1016\/j.dsp.2026.106349_bib0012","series-title":"European Conference on Computer Vision","first-page":"496","article-title":"Stereo depth estimation with echoes","author":"Zhang","year":"2022"},{"key":"10.1016\/j.dsp.2026.106349_bib0013","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2024.104734","article-title":"Target localization algorithm based on improved short-time Fourier transform","volume":"155","author":"Tang","year":"2024","journal-title":"Digit. Signal Process."},{"key":"10.1016\/j.dsp.2026.106349_bib0014","series-title":"IEEE Conference on Artificial Intelligence","first-page":"1063","article-title":"PANO-ECHO: PANOramic depth prediction enhancement with ECHO features","author":"Liu","year":"2024"},{"key":"10.1016\/j.dsp.2026.106349_bib0015","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.dsp.2017.11.003","article-title":"Short-time Fourier transform with the window size fixed in the frequency domain","volume":"77","author":"Mateo","year":"2018","journal-title":"Digit. Signal Process."},{"issue":"6","key":"10.1016\/j.dsp.2026.106349_bib0016","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","article-title":"WavLM: large-scale self-supervised pre-training for full stack speech processing","volume":"16","author":"Chen","year":"2022","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"10.1016\/j.dsp.2026.106349_bib0017","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4009","article-title":"AdaBins: depth estimation using adaptive bins","author":"Bhat","year":"2021"},{"key":"10.1016\/j.dsp.2026.106349_bib0018","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5033","article-title":"Trap attention: monocular depth estimation with manual traps","author":"Ning","year":"2023"},{"key":"10.1016\/j.dsp.2026.106349_bib0019","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10106","article-title":"UniDepth: universal monocular metric depth estimation","author":"Piccinelli","year":"2024"},{"key":"10.1016\/j.dsp.2026.106349_bib0020","article-title":"A robust deep learning pipeline for multi-class cervical cancer cell identification","volume":"32","author":"Eliwa","year":"2025","journal-title":"Egypt. Inform. J."},{"key":"10.1016\/j.dsp.2026.106349_bib0021","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9492","article-title":"Repurposing diffusion-based image generators for monocular depth estimation","author":"Ke","year":"2024"},{"key":"10.1016\/j.dsp.2026.106349_bib0022","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"3203","article-title":"DepthFM: fast generative monocular depth estimation with flow matching","author":"Gui","year":"2025"},{"key":"10.1016\/j.dsp.2026.106349_bib0023","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"5861","article-title":"Attention attention everywhere: monocular depth prediction with skip attention","author":"Agarwal","year":"2023"},{"key":"10.1016\/j.dsp.2026.106349_bib0024","series-title":"Advances in Neural Information Processing Systems","first-page":"53025","article-title":"IEBins: iterative elastic bins for monocular depth estimation","author":"Shao","year":"2023"},{"key":"10.1016\/j.dsp.2026.106349_bib0025","doi-asserted-by":"crossref","first-page":"3964","DOI":"10.1109\/TIP.2024.3416065","article-title":"BinsFormer: revisiting adaptive bins for monocular depth estimation","volume":"33","author":"Li","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.dsp.2026.106349_bib0026","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6262","article-title":"Scalable autoregressive monocular depth estimation","author":"Wang","year":"2025"},{"issue":"2","key":"10.1016\/j.dsp.2026.106349_bib0027","first-page":"265","article-title":"Monocular depth estimation based on audio-visual fusion coupling coordinate self-attention","volume":"37","author":"Ma","year":"2025","journal-title":"J. Comput.-Aided Des. Comput. Graph."},{"key":"10.1016\/j.dsp.2026.106349_bib0028","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.dsp.2026.106349_bib0029","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.dsp.2026.106349_bib0030","series-title":"International Conference on Learning Representations","first-page":"1","article-title":"Deformable DETR: deformable transformers for end-to-end object detection","author":"Zhu","year":"2021"},{"key":"10.1016\/j.dsp.2026.106349_bib0031","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"22578","article-title":"EchoDiffusion: waveform conditioned diffusion models for echo-based depth estimation","author":"Zhang","year":"2025"},{"key":"10.1016\/j.dsp.2026.106349_bib0032","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"28285","article-title":"ECoDepth: effective conditioning of diffusion models for monocular depth estimation","author":"Patni","year":"2024"},{"key":"10.1016\/j.dsp.2026.106349_bib0033","series-title":"Medical Image Computing and Computer Assisted Intervention","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.dsp.2026.106349_bib0034","unstructured":"J. Straub, T. Whelan, L. Ma, Y. Chen, E. Wijmans, S. Green, J.J. Engel, R. Mur-Artal, C. Ren, S. Verma, et al., The Replica dataset: a digital Replica of indoor spaces, 2019, arXiv preprint arXiv: 1906.05797."},{"key":"10.1016\/j.dsp.2026.106349_bib0035","series-title":"International Conference on 3D Vision","first-page":"667","article-title":"Matterport3D: learning from RGB-D data in indoor environments","author":"Chang","year":"2017"},{"key":"10.1016\/j.dsp.2026.106349_bib0036","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9339","article-title":"Habitat: a platform for embodied AI research","author":"Savva","year":"2019"},{"key":"10.1016\/j.dsp.2026.106349_bib0037","series-title":"European Conference on Computer Vision","first-page":"17","article-title":"SoundSpaces: audio-visual navigaton in 3D environments","author":"Chen","year":"2020"},{"key":"10.1016\/j.dsp.2026.106349_bib0038","series-title":"International Conference on Learning Representations","first-page":"1","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"},{"key":"10.1016\/j.dsp.2026.106349_bib0039","series-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"1","article-title":"The audio-visual batvision dataset for research on sight and sound","author":"Brunetto","year":"2023"}],"container-title":["Digital Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1051200426004677?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1051200426004677?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T07:24:26Z","timestamp":1784532266000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1051200426004677"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":39,"alternative-id":["S1051200426004677"],"URL":"https:\/\/doi.org\/10.1016\/j.dsp.2026.106349","relation":{},"ISSN":["1051-2004"],"issn-type":[{"value":"1051-2004","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"WaCoDepth: Waveform conditioned dual-stage feature fusion network for echo-visual depth estimation","name":"articletitle","label":"Article Title"},{"value":"Digital Signal Processing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.dsp.2026.106349","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"106349"}}